Downloads · 30 days
6
8% of all-time downloads
Qwen1.5-0.5B-Chat-ORCA-cDPO
emmabhl/Qwen1.5-0.5B-Chat-ORCA-cDPO
Qwen1.5-0.5B-Chat-ORCA-cDPO is a text generation model from emmabhl. Use it when you need the model to write or continue text. It is set up for peft.
Qwen1.5-0.5B-Chat DPO fine-tuned on the Orca Math dataset that consists of ~200K grade school math word problems
All-time downloads
74
Public
Repo size
15.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 MB · 57%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- May 29, 2024
- Updated
- May 29, 2024
- SHA
- a08f93c7
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen1.5-0.5B-Chat with EPFL DPO fine-tuning
Qwen1.5-0.5B-Chat DPO fine-tuned on the Orca Math dataset that consists of ~200K grade school math word problems
Model Details
Model Description
The model was developed during the course Modern Natural Language Processing (CS-552). Its aim is to fine-tune the base model (Qwen/Qwen1.5-0.5B-Chat) to accurately answer open-ended and multiple-choice questions from Orca Math dataset
- Developed by: Emma Lise Boehly, Ahmed Aziz Ben Haj Hmida and Jan Kokla
- Finetuned from model: Qwen/Qwen1.5-0.5B-Chat
Training Details
Training Data
HuggingFace dataset : microsoft/orca-math-word-problems-200k
Training Procedure
Training Hyperparameters
-
Training regime: cDPO with bf16 mixed precision, $\beta=0.2$, $lr=3 \times 10^{-6}$, and $label_smoothing=0.2$
-
PEFT 0.10.0
- Task
- Text Generation
- Library
- peft
- Languages
- en
- Created
- May 29, 2024
- Updated
- May 29, 2024